Identifying activity level related movement features of children with ASD based on ADOS videos.

Researchers created a computer program that can watch videos of children during autism assessments and measure how much they move around. The program tracked movement of the neck, wrist, and hips during different play activities. When comparing the computer's measurements to what trained clinicians observed, they found strong agreement, especially during table-play activities. This technology could help make autism assessments more consistent and available when there aren't enough specialists.

This study developed a computer vision-based system to automatically assess activity levels in children with ASD using ADOS assessment videos. Researchers extracted movement features (pixel distance and instantaneous pixel velocity) from key body points (neck, right wrist, middle hip) during five standardized activities. The system showed strong correlations (>0.6, p<0.001) with clinician ratings, particularly for table-play activities using pixel distance measures across all body points and velocity measures for right wrist movements. This technology could potentially assist in standardizing ASD assessments and addressing clinician shortages by providing objective, automated evaluation tools for clinical diagnostic processes.

Technology could potentially standardize activity level assessment in autism diagnosis and help address clinician shortages. However, this represents an assistive tool rather than replacement for clinical judgment. Further validation with larger samples and diverse populations needed before clinical implementation. Could enhance objectivity and consistency in ADOS administration.

Sample size not reported, limiting generalizability. Study focused only on activity level assessment rather than comprehensive autism diagnosis. Validation limited to correlation with existing clinician ratings rather than independent diagnostic outcomes. Unclear if results generalize across different ADOS settings or populations.

Autism spectrum disorder (ASD) is a neurodevelopmental disorder that affects about 2% of children. Due to the shortage of clinicians, there is an urgent demand for a convenient and effective tool based on regular videos to assess the symptom. Computer-aided technologies have become widely used in clinical diagnosis, simplifying the diagnosis process while saving time and standardizing the procedure. In this study, we proposed a computer vision-based motion trajectory detection approach assisted with machine learning techniques, facilitating an objective and effective way to extract participants' movement features (MFs) to identify and evaluate children's activity levels that correspond to clinicians' professional ratings.

The designed technique includes two key parts: (1) Extracting MFs of participants' different body key points in various activities segmented from autism diagnostic observation schedule (ADOS) videos, and (2) Identifying the most relevant MFs through established correlations with existing data sets of participants' activity level scores evaluated by clinicians. The research investigated two types of MFs, i.e., pixel distance (PD) and instantaneous pixel velocity (IPV), three participants' body key points, i.e., neck, right wrist, and middle hip, and five activities, including Table-play, Birthday-party, Joint-attention, Balloon-play, and Bubble-play segmented from ADOS videos. Among different combinations, the high correlations with the activity level scores evaluated by the clinicians (greater than 0.6 with p < 0.001) were found in Table-play activity for both the PD-based MFs of all three studied key points and the IPV-based MFs of the right wrist key point. These MFs were identified as the most relevant ones that could be utilized as an auxiliary means for automating the evaluation of activity levels in the ASD assessment.